BannerHistory_example_2016-09-28.ipynb

{
 "metadata": {
  "name": "AndyRussG_BannerHistory_errors"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "SAMPLE_SIZE = 200\nPAST_HOUR_RANGE = 2160 # 90 days * 24 hrs\n\nimport json\nfrom datetime import datetime, timedelta\n\nevents = []\n\nfor _ in range( SAMPLE_SIZE ):\n    h = random.randint( 0, PAST_HOUR_RANGE - 1 )\n    dh = datetime.today() - timedelta( hours = h )\n    f_name = \"/wmf/data/raw/eventlogging/eventlogging_CentralNoticeBannerHistory/hourly/\" + \\\n        \"{}/{:02d}/{:02d}/{:02d}\".format( dh.year, dh.month, dh.day, dh.hour )\n    rdd = sc.sequenceFile( f_name )\n    event = json.loads(rdd.first()[1])['event']\n    events.append(event)\n\nerrors = [event['e'] for event in events if 'e' in event]\nerrors",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 1,
       "text": "[u'LocalStorage not available.',\n u'LocalStorage not available.',\n u'LocalStorage not available.',\n u'LocalStorage not available.']"
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "len(events)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": "200"
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "len(errors)",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": "4"
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}